Distributed Learning with Dependent Samples
This work addresses the challenge of distributed learning for non-independent data, which is incremental as it builds on existing methods for i.i.d. samples.
The paper tackles the problem of analyzing learning rates for distributed kernel ridge regression with dependent (strong mixing) samples, extending the applicable range from i.i.d. to non-i.i.d. sequences and deriving optimal learning rates as a result.
This paper focuses on learning rate analysis of distributed kernel ridge regression for strong mixing sequences. Using a recently developed integral operator approach and a classical covariance inequality for Banach-valued strong mixing sequences, we succeed in deriving optimal learning rate for distributed kernel ridge regression. As a byproduct, we also deduce a sufficient condition for the mixing property to guarantee the optimal learning rates for kernel ridge regression. Our results extend the applicable range of distributed learning from i.i.d. samples to non-i.i.d. sequences.